Forecast Errors

For automatic model selection in Service Parts Planning (SPP), the forecast errors described below are available. Specify in the forecast profile on the Model Selection tab page in the Forecast Error in Automatic Model Selection field which of these forecast errors you want to work with. You get to the forecast profile from the SAP Easy Access screen under Start of the navigation path Service Parts Planning (SPP) Next navigation step Planning Forecasting Forecast Profile End of the navigation path .

Calculation of Forecast Errors

n specifies the number of periods over which the system calculates the standard deviation. You define this parameter dependent on model in the forecast profile on the Model Parameter tab page. For more information, see Calculation of Standard Deviation .

For each forecast model in the forecast profile, you can specify which historical analysis period the system should consider, as described in the following table:

Forecast Model	Historical Analysis Period
First-order exponential smoothing	Details in field Periods for First-Order Exponential Smoothing on the tab page Model Selection
Second-order exponential smoothing	Details in field Periods for Second-Order Exponential Smoothing on the tab page Model Selection
Moving average	Details in field Simulation Periods on the tab page Model Selection and details in the field Maximum Window Length in Moving Average Model on the tab page Model Selection
Linear regression model	Details in field Simulation Periods on the tab page Model Selection and details in the field Periods for Trend Line in LR Model on the tab page Model Parameter
Intermittent forecast model	Details in field Simulation Periods on the tab page Model Selection and details in the field I nitialization Periods for Intermittent Forecast Model on the tab page Model Parameter
Declining demand forecast (DDF)	Details in field Periods in Declining Demand Forecast on the tab page Model Parameter

Mean Percentage Error (MPE)

The system calculates the mean percent error using the following formula:

This graphic is explained in the accompanying text.

Mean Absolute Percentage Error (MAPE)

The system calculates the mean absolute percent error using the following formula:

This graphic is explained in the accompanying text.

Mean Square Error (MSE)

The system calculates the mean square error using the following formula:

This graphic is explained in the accompanying text.

Root of the Mean Square Error (RMSE)

The system calculates the root of the mean square error using the following formula:

This graphic is explained in the accompanying text.

Customer-Defined Forecast Error

In addition to the forecast errors described above that are delivered by us, you can also work with your own forecast errors. In this instance, you must implement the Business Add-In (BAdI) BAdI: Define Customer's Own Forecast Errors (/SAPAPO/BADI_FCST_ERROR). Start of the navigation path For more information, see the Implementation Guide (IMG) forAdvanced Planning and OptimizationunderSupply Chain Planning Next navigation step Service Parts Planning (SPP) Business Add-Ins for Service Parts Planning (SPP) BAdIs for Forecasting BadI: Determine Customer-Defined Forecast Errors. End of the navigation path

Displaying Forecast Errors

You can view the forecast error that the system has calculated on the Interactive Forecasting screen in the Demand: Forecast Error: AMS key figure.

You get to the Interactive Forecasting screen on the SAP Easy Access screen under Start of the navigation path Advanced Planning and Optimization Next navigation step Service Parts Planning (SPP) Planning Forecasting End of the navigation path .